CoChat

Multi-Oriented Object Detection in Aerial Images With Double Horizontal Rectangles

Nie, Guangtao, Huang, Hua · 2022 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Cited by 50

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

Most existing methods adopt the quadrilateral or rotated rectangle representation to detect multi-oriented objects. Yet, the same oriented object may correspond to several different representations, due to different vertex ordering, or angular periodicity and edge exchangeability. To ensure the uniqueness of the representation, some engineered rules are usually added. This makes these methods suffer from discontinuity problem, resulting in degraded performance for objects around some orientation. In this article, we propose to encode the multi-oriented object with double horizontal rectangles (DHRec) to solve the discontinuity problem. Specifically, for an oriented object, we arrange the horizontal and vertical coordinates of its four vertices in left-right and top-down order, respectively. The first (resp. second) horizontal box is given by two diagonal points with smallest (resp. second) and third (resp. largest) coordinates in both horizontal and vertical dimensions. We then regress three factors given by area ratios between different regions, helping to guide the oriented object decoding from the predicted DHRec. Inherited from the uniqueness of horizontal rectangle representation, the proposed method is free of discontinuity issue, and can accurately detect objects of arbitrary orientation. Extensive experimental results show that the proposed method significantly improves the existing baseline representation, and outperforms state-of-the-art methods. The code is availab…

Overview

Integrity signals

Registry

Crossref · 10.1109/tpami.2022.3191753

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 16 references

Research works printed but not linked: 45

  1. 10.1109/TGRS.2012.2207123 · DOI · Paper page
  2. 10.1109/TGRS.2016.2569141 · DOI · Paper page
  3. 10.1109/TGRS.2017.2778300 · DOI · Paper page
  4. 10.1109/TMM.2018.2818020 · DOI · Paper page
  5. 10.1109/ICCV.2019.00832 · DOI · Paper page
  6. 10.1109/TIP.2018.2825107 · DOI · Paper page
  7. 10.1109/TPAMI.2020.2974745 · DOI · Paper page
  8. 10.1109/TGRS.2020.2981203 · DOI
  9. 10.1007/978-3-030-58598-3_40 · DOI · Paper page
  10. 10.1609/aaai.v35i3.16347 · DOI · Paper page
  11. 10.1109/CVPR46437.2021.01556 · DOI · Paper page
  12. Yang, Rethinking rotated object detection with gaussian wasserstein distance loss, 11830
  13. 10.1109/LGRS.2021.3115110 · DOI
  14. 10.1007/978-3-030-58558-7_12 · DOI · Paper page
  15. 10.3390/rs11242930 · DOI · Paper page
  16. 10.3390/rs12030389 · DOI
  17. 10.1109/ICCV.2015.169 · DOI · Paper page
  18. Dai, R-FCN: Object detection via region-based fully convolutional networks, 379
  19. 10.1109/TPAMI.2019.2956516 · DOI · Paper page
  20. 10.1109/CVPR.2017.690 · DOI · Paper page
  21. 10.1109/TPAMI.2018.2858826 · DOI · Paper page
  22. 10.1109/CVPR.2019.00093 · DOI · Paper page
  23. 10.1109/TPAMI.2020.3032166 · DOI · Paper page
  24. 10.1109/TIP.2020.3002345 · DOI · Paper page
  25. 10.1109/TGRS.2019.2930982 · DOI · Paper page
  26. 10.1109/CVPR46437.2021.00281 · DOI · Paper page
  27. 10.1609/aaai.v35i4.16426 · DOI · Paper page
  28. 10.1109/tgrs.2021.3062048 · DOI · Paper page
  29. 10.1109/CVPR42600.2020.01122 · DOI · Paper page
  30. 10.1109/CVPR.2012.6247787 · DOI · Paper page
  31. 10.1109/CVPR.2017.371 · DOI · Paper page
  32. 10.1109/CVPR.2018.00788 · DOI · Paper page
  33. 10.1109/CVPR.2018.00619 · DOI · Paper page
  34. 10.1109/TIP.2019.2900589 · DOI · Paper page
  35. 10.1016/j.patcog.2019.06.020 · DOI
  36. 10.1109/CVPR.2017.283 · DOI · Paper page
  37. 10.1007/s11263-021-01459-7 · DOI
  38. 10.5220/0006120603240331 · DOI · Paper page
  39. 10.1109/ICDAR.2015.7333942 · DOI · Paper page
  40. 10.1109/ICDAR.2017.237 · DOI · Paper page
  41. 10.1109/CVPR.2019.00537 · DOI · Paper page
  42. 10.1109/CVPR42600.2020.00978 · DOI · Paper page
  43. 10.1007/978-3-319-10602-1_48 · DOI · Paper page
  44. 10.1109/TGRS.2020.3010051 · DOI · Paper page
  45. 10.1109/tpami.2022.3166956 · DOI · Paper page

Cited by

Metadata

Authors
Nie, G., & Huang, H.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2022
Pages
1-13
ISSN
  • 0162-8828
  • 2160-9292
  • 1939-3539
Cited by
50
References
16

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.